學習資源常分散在不同的學習主機，因此以代理人方式協助學習者搜尋教學資源已成為重要研究課題。在此我們提出一個行動代理人的技術，讓學習者在分散式學習主機架構下快速找到學習資源。由於行動代理人必須在分散式主機之網路架構下巡行，因此我們該搜索問題轉化成路徑最佳化問題，並提出以蟻式演算法來解決該問題的方法。經實驗模擬結果顯示，學習者的蟻式代理人的數目越多，搜尋能力越強，可較早得到最佳解。學習主機之間的距離越短，越能快速找到最佳化路徑。

Learning resources are usually located among distributed learning hosts. The retrieval of distributed learning resources by agent technology for learner becomes more important. In this paper, a mobile agent method is proposed for the retrieval of learning resources. The retrieval problem is converted into the shortest path optimization problem because the mobile agent has to traverse all of the learning hosts once. A modified ant algorithm is proposed to solve the retrieval problem. In our simulation experiments, the more learner’s ant agents, the more searching ability and can have better solutions. The less distance from learning hosts, the fast to find the optimal path.

中文摘要 i
英文摘要 ii
誌謝 iii
目 錄 iv
表目錄 vi
圖目錄 vii
第一章 導論 1
1.1 研究動機 1
1.2 研究目的 1
1.3 論文章節介紹 2
第二章 相關研究 3
2.1 e-Learning 3
2.1.1 e-Learning定義 4
2.2 代理人 6
2.2.1 代理人定義 6
2.2.2 代理人技術的應用 10
2.3 蟻群演算法之相關文獻 13
2.3.1 螞蟻演算法原理 15
2.3.2 螞蟻系統模型 17
2.4 Ant-Q算法 20
2.5 螞蟻演算法的應用 21
2.5.1 電力系統應用 21
2.5.2 通信系統應用 22
2.5.3 工程應用領域 23
第三章 分散式學習資源搜尋問題之定義 24
3.1 路徑決策組合最佳化問題 25
3.2 教學搜尋模型之探討 26
第四章 建立蟻式代理人系統 28
4.1蟻式代理人系統流程 30
4.2 蟻式代理人參數設定說明 31
第五章 實驗結果 34
第六章 結論 39
參考文獻 40

[1] J. M. Rosenberg, “E-Learning: Strategies for delivering Knowledge in the digital age,” U.S.A:McGraw-Hill, 2001.
[2] 劉仲矩(民91), 大學生對未來遠距教學相關事項看法之研究, 銘傳大學製商整合計劃研討會論文集.
[3] 曹世亮(民90), 永續學習的e-Learning架構：以學習型組織為基礎的探討.資訊與教育雜誌特刊, pp. 163-179.
[4] O. Etzioni, D. S. Weld, “Intelligent Agents on the Internet: Fact, Fiction, and Forecast,” IEEE Expert, pp. 44-49, 1995.
[5] P. Maes, ”Agent that Reduce Work and Information Overload,” Communications of ACM, vol. 37, no. 7, pp. 31-40, 1994.
[6] 王淑卿、張寶儒(2000), “在主從式多代理人架構下資訊擷取最適化之研究,” 朝陽大學資訊管理學系碩士論文。
[7]D. B. Lange, M. Oshima, “Seven good reasons for mobile agents,” Communication of the ACM, vol. 42, no. 3, pp. 88-89, 1999.
[8] H. Lieberman,“Integrating user interface agents with conventional applications,”Knowledge-Based Systems, vol. 11, issue: 1, pp. 15-23, September 30, 1998.
[9] T. Magedanz, K. Rothermel, and S. Krause, “Intelligent Agents: An Emerging Technology for Next Generation Telecommunication,” Proc. INFOCOM’96, San Francisco, CA, 1996.
[10] G. Weis, “Distributed reinforcement learning,” Robotics and Autonomous Systems, vol. 15, issue: 1-2, pp. 135-142, July 1995.
[11]D. Wang, G. Yu, M. Lv, B. Song, D. Shen, and G. Wang, “An ant algorithm based dynamic routing strategy for mobile agents,” Springer-Verlag Berlin Heidelberg, pp. 453-464, 2003.
[12]T. Izumi, T. Masuzawa, “Ant-based approach to mobile agent traversal,” Springer-Verlag Berlin Heidelberg, pp. 350-363, 2004.
[13]C. H. Lee, S. G. Han, “Educational contents sharing and retrieving system using mobile agent,” Proceedings of the International Conference on Computers in Education (ICCE’02), pp. 50-54, 2002.
[14]H. Nunes, S. Labidi, “Mobile Agent for information extraction in MathNet system,” IEEE Forntiers in Education Conference, vol. 2, pp. 20-25, November 2002.
[15]C. Teixeira, S. Labidi, E. Nascimento, “Modeling the cooperative learner based on it’s actions and interactions within a teaching-learning session,” IEEE Forntiers in Education Conference, vol. 2, pp. 19-23, November 2002.
[16]S. Labidi, N. Sergio, “Student modeling and semi-automatic domain ontology construction for shiecc,” IEEE Forntiers in Education Conference, pp. 14-18, October 2000.
[17]R. D. Burke, K. J. Hammond, V. Kulyukin, S. L. Lytinen, N. Tomuro, S. Schoenberg, “Question answering from frequently-asked question files: experiences with the faq finder system,” AI Magazine, vol. 18, no. 2, pp. 57-66, 1997.
[18]M. Dorigo, V. Maniezzo, A. Colorni, “The ant system: optimization by colony of coorperating agents,” IEEE Trans. System, Man, and Cybernetics - Part B, vol. 26 , no. 1, pp. 29-41, 1996.
[19]L. M. Gambardella, M. Dorigo, “Ant colony system: a cooperative learning approach to the traveling salesman problem,” IEEE Trans. System, Man, and Cybernetics - Part B, vol. 1, no. 1, pp. 53-66, 1997.
[20] M. Dorigo, G. D. Caro, L. M. Gambardella, “Ant Algorithms for Discrete Optimization,” Artificial Life, vol. 5, no. 3, pp. 137-172, 1999.
[21] V. Maniezzo, A. Colorni, “The ant system applied to the quadratic assignment problem,” IEEE Transactions on Knowledge and Data Engineering, vol. 11, no. 5, pp. 769-778, 1999.
[22]L. M. Gambardella, M. Dorigo, “Ant-Q: a reinforcement learning approach to the traveling salesman problem,” Proceedings of ML-95, Twelfth International Conference on Machine Learning, A. Prieditis and S. Russell (Eds.), Morgan Kaufmann, pp. 252-260, 1995.
[23] T. Stutzle, “MAX-MIN Ant System for Quadratic Assignment Problems,” Technical Report AIDA-97-04, Intellectics Group, Department of Computer Science, Darmstadt University of Technology, July 1997.
[24] T. Stutzle, H. H. Hoos, “The MAX-MIN Ant System and Local Search for the Traveling Salesman Problem,” Proceedings of the IEEE International Conference on Evolutionary Computation(ICEC’97), pp. 309-314, 1997.
[25] E. D. Taillard, L. M. Grmbardwlla, “Adaptive Memories for the Quadratic Assignment Problem,” Technical Report IDSIA-87-97, IDSIA, Lugano, Switzerland, 1997.